文献类型：期刊文献

英文题名：Optimal Support Vector Machines for forest above-ground biomass estimation from multisource remote sensing data

作者：Guo, Ying[1,2] Li, Zengyuan[1,2] Zhang, Xu[1,2] Chen, Er-Xue[1,2] Bai, Lina[1,2] Tian, Xin[1,2] He, Qisheng[3] Feng, Qi[1,2] Li, Wenmen[1,2]

第一作者：Guo, Ying;郭颖

通信作者：Guo, Y.

机构：[1] Institute of Forest Resources Information Techniques, Chinese Academy of Forestry, Beijing 100091, China; [2] Remote Sensing and Information Technology, State Forestry Administration Key Lab, Beijing 100091, China; [3] Hohai University, Nanjing 211100, China

年份：2012

起止页码：6388-6391

外文期刊名：International Geoscience and Remote Sensing Symposium (IGARSS)

收录：EI(收录号：20130615991854)

语种：英文

外文关键词：Decision trees - Remote sensing - Feature Selection - Biomass - Geology

摘要：The main objective of this study was to investigate the potential of using Support Vector Machines (SVM) and Random forest (RF) to estimate forest above ground biomass (FAGB) by using multi-source remote sensing data. To do so, we introduced a basic flow of SVM to estimate FAGB from multisource remote sensing data. RF method was adept at identifying relevant features having main effects in multisource remote sensing data. Results show that: (i) In the stage of feature selection, the Random Forest model provide better results compared to the typical F-scores method. (ii) The optimal SVM model, based on the selection of features clearly demonstrate that the estimation accuracy increased by feature selection algorithm. (iii) Compared to the optimal KNN, BPNN and RBFNN model, the optimal SVM algorithm provided more accurate and robust result on the considered case. ? 2012 IEEE.